Tagged
Convex Optimization
ML Math Derivations (4): Convex Optimization Theory
Nearly every ML algorithm is an optimization problem. This article derives convex sets, convex functions, gradient descent, Newton's method, KKT conditions, and ADMM -- the optimization toolkit for machine learning.
Matrix Calculus and Optimization -- The Engine Behind Machine Learning
Adjusting the shower temperature is a tiny version of training a neural network: you change a parameter based on an error signal. Matrix calculus is the language that scales this idea to millions of parameters, and …